AGI Strategies

person

Geoffrey Irving

Chief Scientist of UK AI Safety Institute; debate-protocol researcher

Now chief scientist at the UK AI Safety Institute after DeepMind, OpenAI, and Google Brain. Advances 'debate' scalable-oversight protocols and has proved properties about when honesty can be incentivised.

current Chief Scientist, UK AI Safety Institute
past Staff Research Scientist, Google DeepMind; Research scientist, OpenAI
homepage@geoffreyirving

Strategy positions

Alignment firstendorses

Solve technical alignment before capability thresholds close

Advances formal scalable-oversight protocols (debate, prover-estimator debate) that aim to make honest behaviour the equilibrium strategy.

“We present a new scalable oversight protocol (prover-estimator debate) and a proof that honesty is incentivised at equilibrium.”
≡ tweetProver-Estimator Debate tweet· X/Twitter· 2025-06· direct quote

Closest strategy neighbours

by jaccard overlap

Other people whose strategy tags overlap with Geoffrey Irving's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.

  • Aaron Courville

    shared 1 · J=1.00

    Université de Montréal; Deep Learning textbook co-author

  • Adam Jermyn

    shared 1 · J=1.00

    Anthropic; previously astrophysics

  • Adam Kalai

    shared 1 · J=1.00

    Microsoft Research; AI fairness and safety

  • Agnes Callard

    Agnes Callard

    shared 1 · J=1.00

    University of Chicago philosopher; aspiration theorist

  • Ajeya Cotra

    shared 1 · J=1.00

    Open Philanthropy researcher; 'biological anchors' forecaster

  • Alan Turing

    Alan Turing

    shared 1 · J=1.00

    Founder of theoretical computer science (1912–1954)

Record last updated 2026-04-24.